tokencostauto 0.1.464__tar.gz → 0.1.474__tar.gz

{tokencostauto-0.1.464/tokencostauto.egg-info → tokencostauto-0.1.474}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tokencostauto
-Version: 0.1.464
+Version: 0.1.474
 Summary: To calculate token and translated USD cost of string and message calls to OpenAI, for example when used by AI agents
 Author-email: Trisha Pan <trishaepan@gmail.com>, Alex Reibman <areibman@gmail.com>, Pratyush Shukla <ps4534@nyu.edu>, Thiago MadPin <madpin@gmail.com>
 Project-URL: Homepage, https://github.com/madpin/tokencostaudo

{tokencostauto-0.1.464 → tokencostauto-0.1.474}/pyproject.toml

@@ -11,7 +11,7 @@ tokencostauto = ["model_prices.json"]
 [project]
 
 name = "tokencostauto"
-version = "0.1.464"
+version = "0.1.474"
 
 authors = [
     { name = "Trisha Pan", email = "trishaepan@gmail.com" },

{tokencostauto-0.1.464 → tokencostauto-0.1.474}/tokencostauto/model_prices.json

@@ -9117,6 +9117,7 @@
     },
     "gemini/gemini-2.0-flash": {
         "cache_read_input_token_cost": 2.5e-08,
+        "deprecation_date": "2026-03-31",
         "input_cost_per_audio_token": 7e-07,
         "input_cost_per_token": 1e-07,
         "litellm_provider": "gemini",
@@ -9157,7 +9158,7 @@
     },
     "gemini-2.0-flash-001": {
         "cache_read_input_token_cost": 3.75e-08,
-        "deprecation_date": "2026-02-05",
+        "deprecation_date": "2026-03-31",
         "input_cost_per_audio_token": 1e-06,
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "vertex_ai-language-models",
@@ -9294,6 +9295,7 @@
     },
     "gemini/gemini-2.0-flash-001": {
         "cache_read_input_token_cost": 2.5e-08,
+        "deprecation_date": "2026-03-31",
         "input_cost_per_audio_token": 7e-07,
         "input_cost_per_token": 1e-07,
         "litellm_provider": "gemini",
@@ -9683,6 +9685,7 @@
         "supports_web_search": true
     },
     "openrouter/google/gemini-2.0-flash-001": {
+        "deprecation_date": "2026-03-31",
         "input_cost_per_audio_token": 7e-07,
         "input_cost_per_token": 1e-07,
         "litellm_provider": "openrouter",
@@ -12114,6 +12117,7 @@
         "supports_tool_choice": true
     },
     "xai/grok-3-beta": {
+        "cache_read_input_token_cost": 7.5e-07,
         "input_cost_per_token": 3e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 131072,
@@ -12128,6 +12132,7 @@
         "supports_web_search": true
     },
     "xai/grok-3-fast-beta": {
+        "cache_read_input_token_cost": 1.25e-06,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 131072,
@@ -12142,6 +12147,7 @@
         "supports_web_search": true
     },
     "xai/grok-3-fast-latest": {
+        "cache_read_input_token_cost": 1.25e-06,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 131072,
@@ -12156,6 +12162,7 @@
         "supports_web_search": true
     },
     "xai/grok-3-mini-beta": {
+        "cache_read_input_token_cost": 7.5e-08,
         "input_cost_per_token": 3e-07,
         "litellm_provider": "xai",
         "max_input_tokens": 131072,
@@ -12171,6 +12178,7 @@
         "supports_web_search": true
     },
     "xai/grok-3-mini-fast-beta": {
+        "cache_read_input_token_cost": 1.5e-07,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "xai",
         "max_input_tokens": 131072,
@@ -12186,6 +12194,7 @@
         "supports_web_search": true
     },
     "xai/grok-3-mini-fast-latest": {
+        "cache_read_input_token_cost": 1.5e-07,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "xai",
         "max_input_tokens": 131072,
@@ -12462,6 +12471,7 @@
     },
     "gemini-2.0-flash": {
         "cache_read_input_token_cost": 2.5e-08,
+        "deprecation_date": "2026-03-31",
         "input_cost_per_audio_token": 7e-07,
         "input_cost_per_token": 1e-07,
         "litellm_provider": "vertex_ai-language-models",
@@ -12501,6 +12511,7 @@
     },
     "gemini-2.0-flash-lite": {
         "cache_read_input_token_cost": 1.875e-08,
+        "deprecation_date": "2026-03-31",
         "input_cost_per_audio_token": 7.5e-08,
         "input_cost_per_token": 7.5e-08,
         "litellm_provider": "vertex_ai-language-models",
@@ -12536,7 +12547,7 @@
     },
     "gemini-2.0-flash-lite-001": {
         "cache_read_input_token_cost": 1.875e-08,
-        "deprecation_date": "2026-02-25",
+        "deprecation_date": "2026-03-31",
         "input_cost_per_audio_token": 7.5e-08,
         "input_cost_per_token": 7.5e-08,
         "litellm_provider": "vertex_ai-language-models",
@@ -12669,6 +12680,7 @@
     },
     "gemini/gemini-2.0-flash-lite": {
         "cache_read_input_token_cost": 1.875e-08,
+        "deprecation_date": "2026-03-31",
         "input_cost_per_audio_token": 7.5e-08,
         "input_cost_per_token": 7.5e-08,
         "litellm_provider": "gemini",
@@ -13742,6 +13754,7 @@
         "supports_tool_choice": true
     },
     "xai/grok-3": {
+        "cache_read_input_token_cost": 7.5e-07,
         "input_cost_per_token": 3e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 131072,
@@ -15374,6 +15387,7 @@
         "supports_tool_choice": true
     },
     "xai/grok-3-latest": {
+        "cache_read_input_token_cost": 7.5e-07,
         "input_cost_per_token": 3e-06,
         "litellm_provider": "xai",
         "max_input_tokens": 131072,
@@ -15388,6 +15402,7 @@
         "supports_web_search": true
     },
     "xai/grok-3-mini": {
+        "cache_read_input_token_cost": 7.5e-08,
         "input_cost_per_token": 3e-07,
         "litellm_provider": "xai",
         "max_input_tokens": 131072,
@@ -15403,6 +15418,7 @@
         "supports_web_search": true
     },
     "xai/grok-3-mini-latest": {
+        "cache_read_input_token_cost": 7.5e-08,
         "input_cost_per_token": 3e-07,
         "litellm_provider": "xai",
         "max_input_tokens": 131072,
@@ -15418,6 +15434,7 @@
         "supports_web_search": true
     },
     "xai/grok-3-mini-fast": {
+        "cache_read_input_token_cost": 1.5e-07,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "xai",
         "max_input_tokens": 131072,
@@ -20111,6 +20128,7 @@
         "supports_tool_choice": true
     },
     "deepinfra/google/gemini-2.0-flash-001": {
+        "deprecation_date": "2026-03-31",
         "max_tokens": 1000000,
         "max_input_tokens": 1000000,
         "max_output_tokens": 1000000,
@@ -21283,6 +21301,7 @@
         "output_cost_per_token": 0.0
     },
     "vercel_ai_gateway/google/gemini-2.0-flash-lite": {
+        "deprecation_date": "2026-03-31",
         "input_cost_per_token": 7.5e-08,
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 1048576,
@@ -21571,6 +21590,7 @@
         "output_cost_per_token": 1.5e-05
     },
     "vercel_ai_gateway/google/gemini-2.0-flash": {
+        "deprecation_date": "2026-03-31",
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "vercel_ai_gateway",
         "max_input_tokens": 1048576,
@@ -25959,7 +25979,7 @@
         "mode": "chat",
         "output_cost_per_token": 1.02e-06,
         "supports_function_calling": true,
-        "supports_prompt_caching": false,
+        "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_tool_choice": true
     },
@@ -25973,6 +25993,7 @@
         "output_cost_per_token": 1.75e-06,
         "source": "https://openrouter.ai/z-ai/glm-4.6",
         "supports_function_calling": true,
+        "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_tool_choice": true
     },
@@ -25986,6 +26007,7 @@
         "output_cost_per_token": 1.9e-06,
         "source": "https://openrouter.ai/z-ai/glm-4.6:exacto",
         "supports_function_calling": true,
+        "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_tool_choice": true
     },
@@ -28785,6 +28807,8 @@
         ]
     },
     "zai/glm-4.6": {
+        "cache_creation_input_token_cost": 0,
+        "cache_read_input_token_cost": 1.1e-07,
         "input_cost_per_token": 6e-07,
         "output_cost_per_token": 2.2e-06,
         "litellm_provider": "zai",
@@ -28792,6 +28816,8 @@
         "max_output_tokens": 128000,
         "mode": "chat",
         "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
         "supports_tool_choice": true,
         "source": "https://docs.z.ai/guides/overview/pricing"
     },
@@ -31659,6 +31685,9 @@
         "output_cost_per_token": 0.0
     },
     "azure_ai/claude-haiku-4-5": {
+        "cache_creation_input_token_cost": 1.25e-06,
+        "cache_creation_input_token_cost_above_1hr": 2e-06,
+        "cache_read_input_token_cost": 1e-07,
         "input_cost_per_token": 1e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 200000,
@@ -31677,6 +31706,9 @@
         "supports_vision": true
     },
     "azure_ai/claude-opus-4-1": {
+        "cache_creation_input_token_cost": 1.875e-05,
+        "cache_creation_input_token_cost_above_1hr": 3e-05,
+        "cache_read_input_token_cost": 1.5e-06,
         "input_cost_per_token": 1.5e-05,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 200000,
@@ -31695,6 +31727,9 @@
         "supports_vision": true
     },
     "azure_ai/claude-sonnet-4-5": {
+        "cache_creation_input_token_cost": 3.75e-06,
+        "cache_creation_input_token_cost_above_1hr": 6e-06,
+        "cache_read_input_token_cost": 3e-07,
         "input_cost_per_token": 3e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 200000,
@@ -33240,6 +33275,7 @@
         "supports_function_calling": true,
         "supports_tool_choice": true,
         "supports_prompt_caching": true,
+        "supports_reasoning": true,
         "supports_system_messages": true,
         "max_input_tokens": 1000000,
         "max_output_tokens": 8192
@@ -33254,6 +33290,7 @@
         "supports_function_calling": true,
         "supports_tool_choice": true,
         "supports_prompt_caching": true,
+        "supports_reasoning": true,
         "supports_system_messages": true,
         "max_input_tokens": 1000000,
         "max_output_tokens": 8192
@@ -33268,6 +33305,7 @@
         "supports_function_calling": true,
         "supports_tool_choice": true,
         "supports_prompt_caching": true,
+        "supports_reasoning": true,
         "supports_system_messages": true,
         "max_input_tokens": 200000,
         "max_output_tokens": 8192
@@ -33670,6 +33708,7 @@
         "max_output_tokens": 128000,
         "mode": "chat",
         "supports_function_calling": true,
+        "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_tool_choice": true,
         "source": "https://docs.z.ai/guides/overview/pricing"
@@ -35382,6 +35421,9 @@
         "supports_system_messages": true
     },
     "azure_ai/claude-opus-4-5": {
+        "cache_creation_input_token_cost": 6.25e-06,
+        "cache_creation_input_token_cost_above_1hr": 1e-05,
+        "cache_read_input_token_cost": 5e-07,
         "input_cost_per_token": 5e-06,
         "litellm_provider": "azure_ai",
         "max_input_tokens": 200000,
@@ -35502,8 +35544,11 @@
         "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 1.4e-05,
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
         "supported_modalities": [
             "text",
             "image"
@@ -35521,10 +35566,9 @@
         "max_input_tokens": 128000,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
-        "mode": "chat",
+        "mode": "responses",
         "output_cost_per_token": 1.4e-05,
         "supported_endpoints": [
-            "/v1/chat/completions",
             "/v1/responses"
         ],
         "supported_modalities": [
@@ -36012,5 +36056,121 @@
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": false
+    },
+    "deepseek-v3-2-251201": {
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "volcengine",
+        "max_input_tokens": 98304,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "chat",
+        "output_cost_per_token": 0.0,
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
+    "glm-4-7-251222": {
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "volcengine",
+        "max_input_tokens": 204800,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 0.0,
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
+    "kimi-k2-thinking-251104": {
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "volcengine",
+        "max_input_tokens": 229376,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "chat",
+        "output_cost_per_token": 0.0,
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
+    "gemini-robotics-er-1.5-preview": {
+        "cache_read_input_token_cost": 0,
+        "input_cost_per_token": 3e-07,
+        "input_cost_per_audio_token": 1e-06,
+        "litellm_provider": "gemini",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 65535,
+        "max_tokens": 65535,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-06,
+        "output_cost_per_reasoning_token": 2.5e-06,
+        "source": "https://ai.google.dev/gemini-api/docs/models#gemini-robotics-er-1-5-preview",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_output": false,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": false,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_url_context": true,
+        "supports_vision": true,
+        "supports_web_search": true
+    },
+    "gemini/gemini-robotics-er-1.5-preview": {
+        "cache_read_input_token_cost": 0,
+        "input_cost_per_token": 3e-07,
+        "input_cost_per_audio_token": 1e-06,
+        "litellm_provider": "gemini",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 65535,
+        "max_tokens": 65535,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-06,
+        "output_cost_per_reasoning_token": 2.5e-06,
+        "source": "https://ai.google.dev/gemini-api/docs/models#gemini-robotics-er-1-5-preview",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "video",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_output": false,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": false,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_url_context": true,
+        "supports_vision": true,
+        "supports_web_search": true
     }
 }

{tokencostauto-0.1.464 → tokencostauto-0.1.474/tokencostauto.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tokencostauto
-Version: 0.1.464
+Version: 0.1.474
 Summary: To calculate token and translated USD cost of string and message calls to OpenAI, for example when used by AI agents
 Author-email: Trisha Pan <trishaepan@gmail.com>, Alex Reibman <areibman@gmail.com>, Pratyush Shukla <ps4534@nyu.edu>, Thiago MadPin <madpin@gmail.com>
 Project-URL: Homepage, https://github.com/madpin/tokencostaudo